如何在 CNN 中绘制 epoch vs. val_acc 和 epoch vs. val_loss 图？答案

【问题标题】：How to plot epoch vs. val_acc and epoch vs. val_loss graph in CNN?如何在 CNN 中绘制 epoch vs. val_acc 和 epoch vs. val_loss 图？
【发布时间】：2019-07-11 23:26:58
【问题描述】：

我使用卷积神经网络 (CNN) 来训练数据集。在这里，我将 epoch、val_loss、val_acc、total loss、训练时间等作为历史记录。如果我想计算准确率的平均值，那么如何访问 val_acc，以及如何绘制 epoch vs. val_acc 和 epoch vs. val_loss 图？

convnet = input_data(shape=[None, IMG_SIZE, IMG_SIZE, 3], name='input')
convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 128, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 32, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = conv_2d(convnet, 64, 3, activation='relu')
convnet = max_pool_2d(convnet, 3)

convnet = fully_connected(convnet, 1024, activation='relu')
convnet = dropout(convnet, 0.8)

convnet = fully_connected(convnet, 4, activation='softmax')
convnet = regression(convnet, optimizer='adam', learning_rate=LR, loss='categorical_crossentropy', name='targets')

model = tflearn.DNN(convnet, tensorboard_dir='log')

if os.path.exists('{}.meta'.format(MODEL_NAME)):
   model.load(MODEL_NAME)
   print('model loaded!')

train = train_data[:-150]
test = train_data[-50:]

X = np.array([i[0] for i in train]).reshape(-1,IMG_SIZE,IMG_SIZE,3)
Y = [i[1] for i in train]

test_x = np.array([i[0] for i in test]).reshape(-1,IMG_SIZE,IMG_SIZE,3)
test_y = [i[1] for i in test]

hist=model.fit({'input': X}, {'targets': Y}, n_epoch=8, validation_set=({'input': test_x}, {'targets': test_y}),
snapshot_step=40, show_metric=True, run_id=MODEL_NAME)
model.save(MODEL_NAME)

【问题讨论】：

标签： python python-3.x tensorflow image-processing conv-neural-network

【解决方案1】：

您可以使用callbacks in Tensorflow。特别是，您可以使用Keras callbacks 之类的CSVLogger，它将您的纪元结果流式传输到CSV。从那里您可以进行各种分析。

基于您的代码的示例：

csv_logger = CSVLogger('training.log')
model.fit({'input': X}, {'targets': Y}, ..., callbacks=[csv_logger]

【讨论】：

【解决方案2】：

尝试以下方法：

history = model.fit(X_train, Y_train, validation_data=(X_test, Y_test), batch_size=32, epochs=10, verbose=1)

# Get training and test loss histories
training_loss = history.history['loss']
test_loss = history.history['val_loss']

# Create count of the number of epochs
epoch_count = range(1, len(training_loss) + 1)

# Visualize loss history
plt.plot(epoch_count, training_loss, 'r--')
plt.plot(epoch_count, test_loss, 'b-')
plt.legend(['Training Loss', 'Test Loss'])
plt.xlabel('Epoch')
plt.ylabel('Loss')
plt.show();

感谢https://chrisalbon.com/deep_learning/keras/visualize_loss_history/

【讨论】：